Skip to content
AI Atlas
Diff the AI world

What changed between 15 Sept 2026 and 16 Sept 2026

Two dates, one scope: new and retired models, price and context changes, new benchmark leaders, new papers, provider and hardware changes. Built from the change log keyed on when things occurred — nothing is inferred, and the URL is the report.

Scope: the whole atlas

Reset

1,377 events in the window · 2,613 claims superseded · price rows opened 12 / closed 12 · entities at 15 Sept 2026: 8,014 → at 16 Sept 2026: 8,515. The entity lists are capped at 200 by the API — per-type counts below are “of the first 200”. Events are keyed on occurred_at (effective date when known) and exclude back-filled history unless include_backfill=1; new_entities uses first_seen_at. new_benchmark_leaders compares the primary-group leader computed from results observed by each date.

New models

New models 1

New models
ModelOrganizationParamsContextOpennessReleasedFirst seen
OpenELM-1_1BApple1.08Brestricted-weights12 Apr 202416 Sept 2026

Retired models

Retired models 0

No model was retired between these dates

Price changes

Price changes 8

Price changes
DateModelProviderInput / 1MOutput / 1MSource
Mistral Small 3.2 24BOpenRouter$0.075$0.094+25.0%$0.20$0.25+25.0%openrouter.ai
GLM 5.3 FlashOpenRouter$0.075$0.10+33.3%$0.25$0.333+33.3%openrouter.ai
DeepSeek-V4-Pro-0813OpenRouter$0.66$0.983+49.0%$1.98$2.95+49.0%openrouter.ai
MiniMax M1OpenRouter$0.55$0.40−27.3%$2.2$2.20.0%openrouter.ai
Nemotron 3 UltraOpenRouter$0.60$0.625+4.2%$2.4$3.13+30.2%openrouter.ai
Qwen3 VL 30B A3B InstructOpenRouter$0.13$0.15+15.4%$0.52$0.60+15.4%openrouter.ai
Qwen3 VL 30B A3B InstructOpenRouter$0.15$0.13−13.3%$0.60$0.52−13.3%openrouter.ai
Kimi K2.7 CodeOpenRouter$0.71$0.706−0.5%$3.5$3.21−8.3%openrouter.ai

Context changes

Context changes 3

Context changes
DateModelOrganizationContext windowSourceHistory
Qwen3 VL 30B A3B InstructQwen32.8K tokens16.4K tokens−50.0%openrouter.ai claims →
Qwen3 VL 30B A3B InstructQwen16.4K tokens32.8K tokens+100.0%openrouter.ai claims →
Nemotron 3 UltraNVIDIA182.5K tokens32.8K tokens−82.0%openrouter.ai claims →

New benchmark leaders

New benchmark leaders 0

Benchmarks whose primary-group leader (computed from results observed by each date) differs between 15 Sept 2026 and 16 Sept 2026.

No benchmark changed leader between these dates

New papers

New papers 198

New papers
PaperOrganizationPublishedFirst seen
A multimodal large language model for evidence-based autism spectrum disorder screening16 Sept 202616 Sept 2026
Measuring Annotation Efficiency for Handwritten Devanagari Recognition: Sample-Complexity Curves for Four Pretraining Regimes16 Sept 202616 Sept 2026
NeuroTS-Net: Multi-Class Semantic Segmentation of Pediatric Brain Tumors in Multi-Modal MRI16 Sept 202616 Sept 2026
From Foundation Embeddings to Cropland Maps: Label Efficiency, Temporal Transferability and Independent Human Validation16 Sept 202616 Sept 2026
MDN-Control: Mask-Depth-Noise Guided Region Control for Multi-Subject Video Editing16 Sept 202616 Sept 2026
Vision And Text Transformer For Predicting Answerability On Visual Question Answering16 Sept 202616 Sept 2026
EgoPathBench: Evaluating Zero-Shot Egocentric Waypoint Decision-Making in Vision-Language Models16 Sept 202616 Sept 2026
PiPS: Post-Hoc Prototypical Explanations for Interpretable Semantic Segmentation16 Sept 202616 Sept 2026
DenseFace: Bias Mitigation in Face Recognition via Density-Aware Probabilistic Matching16 Sept 202616 Sept 2026
Hyper-RED: Scalable Event Pre-training via Semantic Hypergraph Distillation16 Sept 202616 Sept 2026
Hub-Spectral Activation of Latent Multimodal Knowledge16 Sept 202616 Sept 2026
Unlocking Zero-shot Potential of Semi-dense Image Matching via Gaussian Splatting16 Sept 202616 Sept 2026
State of Thought Enables Endogenous Reasoning16 Sept 202616 Sept 2026
Spurious Tool Use: When RL Agents Learn the Wrong Reason to Act16 Sept 202616 Sept 2026
RoleBreak: Benchmarking Long-Horizon Role-Playing Robustness in Spoken Dialogue16 Sept 202616 Sept 2026
TAME: Token Attribution and Masking for Emergent misalignment16 Sept 202616 Sept 2026
ImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals16 Sept 202616 Sept 2026
Bias Audits Detect Bias but Disagree on Ranking: Evidence from Ten Instruments and Ten Frontier Models16 Sept 202616 Sept 2026
Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agents16 Sept 202616 Sept 2026
Speaker-Specific and Language-Dependent Temporal Organization in Bilingual Political Speech16 Sept 202616 Sept 2026
Speaker or Language? Explaining Variance in Charismatic Prosody Across Luxembourgish and French16 Sept 202616 Sept 2026
Efficient One-to-Many Translation with Joint Multi-Stream Diffusion16 Sept 202616 Sept 2026
How Humans and LLMs Read Gender into Gender-Neutral Physical Descriptions16 Sept 202616 Sept 2026
ParsHate: A Benchmark Dataset for Hate and Target Detection in Persian16 Sept 202616 Sept 2026
Negation Beyond the Verbal Channel: Temporal Multimodal Correlates in Dialogue16 Sept 202616 Sept 2026
Beyond the Name: Demographic Leakage in De-Identified R\'esum\'es and Evaluation Artifacts in LLM Bias Audits16 Sept 202616 Sept 2026
Japanese Stroke LLM Evaluation: A Conversational Benchmark for Safe Stroke Care in Japanese Using Large Language Models16 Sept 202616 Sept 2026
A Data-free Universal Prior over Syntactic Structures16 Sept 202616 Sept 2026
Audio-Visual Turn-taking Prediction in Cocktail Party Scenarios16 Sept 202616 Sept 2026
CareMirror: Bringing Caregiver Wellbeing into the Dementia Care Ecosystem16 Sept 202616 Sept 2026
SciNLP: A Domain-Specific Benchmark for Full-Text Scientific Entity and Relation Extraction in NLP16 Sept 202616 Sept 2026
Zero-shot narrative detection in social messaging16 Sept 202616 Sept 2026
Universal Defenses for Tool-Integrated LLM Agents Against Adversarial Attacks16 Sept 202616 Sept 2026
PARSA-Bench: A Comprehensive Persian Audio-Language Model Benchmark16 Sept 202616 Sept 2026
Attention Mean Fields Predict Average Representation Dynamics and Reveal Context-Specific Computation16 Sept 202616 Sept 2026
Decoder Design Matters for ECG Delineation16 Sept 202616 Sept 2026
Stable by Construction: Variational Latent Markov Operators for Long-Horizon PDE Prediction16 Sept 202616 Sept 2026
Learning Options for Compositional Motor Control with Adapter Banks16 Sept 202616 Sept 2026
OptiPrime: Optimizing Private Inference through Protocol-Hardware Co-design16 Sept 202616 Sept 2026
Repurposing Unified Topological Signatures for Graph Representation Learning16 Sept 202616 Sept 2026
Neural Field Ensembles for Aerodynamic Surface Prediction: Winning Solution to the ONERA CRM Wall Distribution 2025 Challenge16 Sept 202616 Sept 2026
3D Field Data Reduction with Adaptive Sample-Based Gaussian-Encoded Reconstruction16 Sept 202616 Sept 2026
Is INT8 Portable? A Cross-Platform Measurement Study of Quantized Inference on Embedded and Automotive Accelerators16 Sept 202616 Sept 2026
EBL: Efficient Broad Learning for Distributed Adaptive Harmonic Analysis16 Sept 202616 Sept 2026
Fast-Convergent Meta-RL via Gradient-Clustered BS Sampling for Edge Caching16 Sept 202616 Sept 2026
HUMAID-NER: A Disaster Tweet Dataset for Joint Named Entity Recognition and Event Classification via Uncertainty-Weighted Multitask Learning16 Sept 202616 Sept 2026
Nepali Legal Expertise through Generative and Extractive Pre-trained Transformers (NepLEGiT)16 Sept 202616 Sept 2026
Efficient Multimodal Generative Recommendation with Latent Narrative Reasoning16 Sept 202616 Sept 2026
RAG-CT: Mitigating Privacy Risks on Retrieval-Augmented Generation Systems via Scanning Prompt Distribution16 Sept 202616 Sept 2026
Competence-Preserving Resume Perturbations Expose Presentation Sensitivity in LLM Screening16 Sept 202616 Sept 2026
Rewarding Reasoning, Not Answers: Fixing and Bounding Test-Time Reinforcement Learning on Medical QA16 Sept 202616 Sept 2026
DiaWhisper-DPO: Role-Attributed Transcription of Clinical Interviews via Failure-Mined Preference Optimization16 Sept 202616 Sept 2026
CLARE: Scalable Class-Incremental Continual Learning via a Sparsity-Based Framework16 Sept 202616 Sept 2026
Smarter by the Moment: Environment-Driven Dynamic Policies for Continual LLM Improvement16 Sept 202616 Sept 2026
AraMIP: Extending MIPVU Towards Metaphor Identification in Arabic16 Sept 202616 Sept 2026
Interpreting and Steering LLM Agents for Social Simulations16 Sept 202616 Sept 2026
Right Direction, Wrong Step: Geometric Analysis of Finite-Step Failure in Looped Transformers16 Sept 202616 Sept 2026
When Confidence Signals Disagree: Local and Global Confidence in Autoregressive Language Models16 Sept 202616 Sept 2026
Distributed JEPA: A Self-Supervised Framework for Energy Forecasting16 Sept 202616 Sept 2026
AsyncCouple-Flow: Asynchronous Cross-Modal Coupling and Flow Matching for Spatio-Temporal Forecasting16 Sept 202616 Sept 2026
A unified framework for global and local interpretability using adaptive derivative-ordered random explanation16 Sept 202616 Sept 2026
Learning-Guided Planning in Large Dynamic Action Spaces: Budgeted Tree Search for One-to-Many Mobile Charging16 Sept 202616 Sept 2026
Molecular representation shapes the balance between target fidelity and exploration in flow based polymer generation16 Sept 202616 Sept 2026
Digital Persuasion: Understanding the Impact of Online Influencers on Public Opinion16 Sept 202616 Sept 2026
Multi-Agent Learning with Cooperation-Driven Optimization Dynamics16 Sept 202616 Sept 2026
Causal Discovery via Transformed Low-Rank Quantile Surfaces16 Sept 202616 Sept 2026
Splitting the Difference: Interpretable Causal Forests for Treatment Effect Heterogeneity and Bias16 Sept 202616 Sept 2026
LoopSpec: Pipelined Self-Speculative Decoding for Looped Transformers16 Sept 202616 Sept 2026
Beyond Measurement Metrics: A Human-Centered Framework for Semantic Validation of Network Traffic Classification16 Sept 202616 Sept 2026
Neuro-Symbolic Hierarchical Intention Anticipation in Human Behavior16 Sept 202616 Sept 2026
Continual Learning for Traversability Prediction with Uncertainty-Aware Adaptation16 Sept 202616 Sept 2026
Cross-Domain Inference for Human Localization: Applying Wi-Fi RSSI Data to CSI-Trained Models16 Sept 202616 Sept 2026
Conformal Policy Learning with Distribution-Free Safety Guarantees16 Sept 202616 Sept 2026
Easy to Catch a Liar, Hard to Clear an Honest One: Language Models Diagnosing a Corrupted Reward Channel from a Verified Record16 Sept 202616 Sept 2026
Strategic Advice in the Age of Personal AI16 Sept 202616 Sept 2026
High-Performance Tensor Formulation of the Viterbi Algorithm for Hidden Semi-Markov Models16 Sept 202616 Sept 2026
Recovering Physical Parameters from Fragmented Observations via Exact Distributed Spline Merging16 Sept 202616 Sept 2026
BenSParX: A Robust Explainable Machine Learning Framework for Parkinson's Disease Detection from Bengali Conversational Speech16 Sept 202616 Sept 2026
Continuous-Time Machine Learning: A Unified Mathematical Perspective16 Sept 202616 Sept 2026
A Systematic Evaluation of Machine Learning Methods for Fault Detection and Line Identification in Electrical Power Grids16 Sept 202616 Sept 2026
Repurposing Deep Limit Order Book Forecasting for Scenario-Conditioned Market Impact Modeling16 Sept 202616 Sept 2026
Predicting Social Media Engagement using Machine Learning16 Sept 202616 Sept 2026
Large Language Models Develop Belief State Geometry In-Context16 Sept 202616 Sept 2026
Compute-Optimal Pretrain--Fine-tune in Ridge Gradient Descent16 Sept 202616 Sept 2026
Towards Surrogate Based Dequantization of Quantum Reinforcement Learning16 Sept 202616 Sept 2026
IRENE: A Convolutional GRU Ensemble Model for Radar Precipitation Nowcasting over Italy16 Sept 202616 Sept 2026
Semantic-Aware Neural Video Codec for Error-Resilient Low-Latency Transmission16 Sept 202616 Sept 2026
Symmetric solution of the Bellman optimality equation for repeated harmony game16 Sept 202616 Sept 2026
Nationally Consistent, Locally Incomplete: A Bayesian Remote-Sensing Audit of Rooftop Photovoltaic Registries16 Sept 202616 Sept 2026
BLINDSPOT: A Benchmark for Safety and Refusal Calibration in Long-Horizon Tool-Using Agents16 Sept 202616 Sept 2026
FairLint-DL: An IDE-Native Tool for Fairness Debugging of Deep Learning Software16 Sept 202616 Sept 2026
Physics Informed Random Feature Neural Networks for Solving PDEs16 Sept 202616 Sept 2026
Knowledge as Orbit: Finite Collections as Phases of an Exactly Periodic Latent Generator16 Sept 202616 Sept 2026
Balancing Trial and Reorder: A Hybrid Sequential Transformer-GBDT Ranker for On-Demand Delivery16 Sept 202616 Sept 2026
The Neverwhere Visual Parkour Benchmark Suite16 Sept 202616 Sept 2026
Not All Relations Are Equal: Relation-Balanced and Calibrated Graph Learning for Provenance-Based Intrusion Detection16 Sept 202616 Sept 2026
MyoFlow: Anchor-Tied Rectified Flow for HD-sEMG Gesture Recognition Across Sessions and Subjects16 Sept 202616 Sept 2026
Certified Inference and Training for Deep Equilibrium Networks: A Continuation Framework with Polynomial Complexity Guarantees16 Sept 202616 Sept 2026
Unified Heterogeneous Graph Neural Network solver for Power Flow, Optimal Power Flow and State Estimation16 Sept 202616 Sept 2026
The Latent That Never Was: A Forensic Re-run of the CVAE Ablation in Action Chunking Transformer16 Sept 202616 Sept 2026
Time-warping estimation via stationarity-based learning of the de-warped signal16 Sept 202616 Sept 2026
Memorisation bias in medical AI16 Sept 202616 Sept 2026
On the disintegration of the stochastic majority vote: From PAC-Bayesian bounds to a self-bounding algorithm16 Sept 202616 Sept 2026
TEMPO: Learning Temporal Context for Dynamic Robot Manipulation16 Sept 202616 Sept 2026
Near-Optimal Nonconvex Matrix Completion16 Sept 202616 Sept 2026
Optimization over covariance matrices with a parameterized metric16 Sept 202616 Sept 2026
Few-Shot Degradation Is Not What It Seems: Behavioral Evidence, Representation Analysis, and a Random-Text Control Across 12 Models, 2 Tasks, and 2 Architectures16 Sept 202616 Sept 2026
Intrinsic Robot Rewarding: Reusing VLA Representations for Autonomous Evaluation and Policy Improvement16 Sept 202616 Sept 2026
Robust Recurrent Reinforcement Learning under Evolving Hidden Disturbances with Application to Rover Wheel Slip16 Sept 202616 Sept 2026
Single Document Extractive Summarization using Domination in Hypergraph16 Sept 202616 Sept 2026
Attention is All You Need Until You Need Retention16 Sept 202616 Sept 2026
Explainable Graph-theoretical Machine Learning with Application to Alzheimer's Disease Prediction16 Sept 202616 Sept 2026
When majority rules, minority loses: bias amplification of gradient descent16 Sept 202616 Sept 2026
Latent Undertow: How Ordinary Typos Break Probes16 Sept 202616 Sept 2026
GraphIFE: Rethinking Graph Imbalance Node Classification via Invariant Learning16 Sept 202616 Sept 2026
Crash Narrative-Guided Countermeasure Recommendation Using Large Language Models: A Retrieval-Augmented Generation Framework for Intersection Safety16 Sept 202616 Sept 2026
Personalized Federated Learning through Global Knowledge Distillation and Local Head Adaptation16 Sept 202616 Sept 2026
Data-Driven Soft Labeling Scales DNA Read Classification to Whole-Body Cell-Type Deconvolution16 Sept 202616 Sept 2026
Neural Operator Learning for Collision-Aware Trajectory Planning of Spacecraft Swarms16 Sept 202616 Sept 2026
GeoCrossBench: Cross-Band Generalization for Remote Sensing16 Sept 202616 Sept 2026
Same Flow, Different Paths: Variance Reduction in Flow Matching16 Sept 202616 Sept 2026
M-Fibration Theory with Applications to Weighted Graphs16 Sept 202616 Sept 2026
Hessian-based molecular conformation augmentation for a scalable and efficient strategy of machine learning interatomic potentials16 Sept 202616 Sept 2026
ViCo: Visual-oriented Coding with Self-Reflection for Chart Replication16 Sept 202616 Sept 2026
Adaptive Anisotropic Attention for Axis-Structured Signals16 Sept 202616 Sept 2026
Are We Grading Properly? Understanding Failure Modes in Medical Benchmarks16 Sept 202616 Sept 2026
Hybrid Variational Quantum Circuits for Multivariate Regression and High-Dimensional Data Reconstruction16 Sept 202616 Sept 2026
Towards Scalable RLVR: Multimodal Instruction Following Data Synthesis and Distillation16 Sept 202616 Sept 2026
Training Energy-Based Models with Non-MCMC Samplers and Efficient Temperature Estimation16 Sept 202616 Sept 2026
Risk-Calibrated Bayesian Streaming Intrusion Detection with SRE-Aligned Decisions16 Sept 202616 Sept 2026
Formalized Hopfield Networks and Boltzmann Machines16 Sept 202616 Sept 2026
TARC: Time-Adaptive Robotic Control16 Sept 202616 Sept 2026
Nonnegative matrix factorizations and related compositional models: Equivalence, identifiability, and an application on the grain-size analysis of sediments16 Sept 202616 Sept 2026
OPEN-1B: A Fully Auditable Training Run16 Sept 202616 Sept 2026
Collaborative Optimization of Multiclass Imbalanced Learning: Density-Aware and Region-Guided Boosting16 Sept 202616 Sept 2026
Universal Feature Selection with Noisy Observations and Weak Symmetry Conditions16 Sept 202616 Sept 2026
Deep-learning-based low-energy trigger algorithms for the Hyper-Kamiokande experiment16 Sept 202616 Sept 2026
CausalSmith: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference16 Sept 202616 Sept 2026
Protecting patient privacy in clinical foundation models: Technical and legal perspectives16 Sept 202616 Sept 2026
Bridging the Confidence Gap: Temperature Scaling for Calibrating Test-Time Prompt Tuning16 Sept 202616 Sept 2026
HoloAegis: Frozen Representation, Topological Inference --- Minimally Parametric Safety Manifolds and Their Capability Boundaries for LLM Guardrails16 Sept 202616 Sept 2026
LaGSplat: Inferring Physics-Governed Interactive Simulation from Monocular Video Using Latent Lagrangian Gaussian Splatting16 Sept 202616 Sept 2026
You Don't Need To Train: Agentic Heuristic Learning Studio for Executable Human Activity Recognition16 Sept 202616 Sept 2026
Driver Behavior Estimation at Signalized Intersections Using a Physics-Constrained Decision-Conditioned Autoregressive Transformer16 Sept 202616 Sept 2026
SWB-DM: A Calibrated Sliced-Wasserstein-Barycenter Aggregator with Delayed-Momentum Caching for Byzantine-Robust Federated Learning under Partial Participation16 Sept 202616 Sept 2026
Reduced-Space Multi-Fidelity Bayesian Optimization of Process Simulation Models16 Sept 202616 Sept 2026
Coupled Calibration and Learning: Mitigating Teacher Bias in LLM Distillation without Target-Domain Reward Feedback16 Sept 202616 Sept 2026
FreqSpaNet: Frequency and Spatial Learning of SFPF for Physical Layer Hardware Integrity Detection16 Sept 202616 Sept 2026
ENCP: Episode-Normalized Conformal Prediction for Vision-and-Language Navigation16 Sept 202616 Sept 2026
Nonsmooth Optimization via Orthogonalized Momentum16 Sept 202616 Sept 2026
Measuring AI harms with multidimensional Lorenz Zonoids16 Sept 202616 Sept 2026
EMODY Flow: Emotion-Aware Audio-Driven Full-Body Motion Generation16 Sept 202616 Sept 2026
A deep dictionary network-based foundation model for ultra-low-dose CT denoising16 Sept 202616 Sept 2026
Computer-assisted global regularity across nonlinear families of three-dimensional periodic Navier-Stokes flows16 Sept 202616 Sept 2026
GPEvac: GNN-Based PPO for Adaptive Evacuation Routing During Shooting Events16 Sept 202616 Sept 2026
Permutation-Based Stegomalware in Large Language Models: Threats and Countermeasures16 Sept 202616 Sept 2026
A Sentinel-2 benchmark dataset for deep-learning active-fire segmentation across 25 California wildfires16 Sept 202616 Sept 2026
Improving Reduced-Order Rotating Detonation Engine Models with Data Assimilation and Machine Learning16 Sept 202616 Sept 2026
Copula Adapted Directed Acyclic Graph for Cluster Representation of Biomedical Data16 Sept 202616 Sept 2026
The AI-Enabled Scientific Frontier16 Sept 202616 Sept 2026
Sequence Recognition in Bharatnatyam dance16 Sept 202616 Sept 2026
Breaking the 1.58-bit Barrier for Ternary LLMs16 Sept 202616 Sept 2026
AURA: Agentic Diagnosis and Refinement for Production Recommender Systems at Scale16 Sept 202616 Sept 2026
Can Knowledge Transfer Parameters Be Learned? LePoKet for Efficient Robotic Vision16 Sept 202616 Sept 2026
Carry-Through Checksum: A Lightweight Fault-Detection for CNN Inference at the Edge16 Sept 202616 Sept 2026
Constant Swap Regret in General-Sum Games via Optimistic Transition Matrices16 Sept 202616 Sept 2026
Lesion-centered 3D mapping of colonoscopy procedures: validation of a hierarchical ensemble pipeline on public benchmark videos16 Sept 202616 Sept 2026
FROD: Feature Matching Residual Denoising Oracle Bone Decipher16 Sept 202616 Sept 2026
Optical-Flow Wingbeat Counting in MuJoCo: A Comparison of Convolutional, Spiking, and Attention-Based Temporal Models16 Sept 202616 Sept 2026
ResLRP: The Role of Residual Cancellation in Attribution Instability in Vision Transformers16 Sept 202616 Sept 2026
StalePO: Anchored Token-Level Preference Optimization using Legacy Post-Edits in Machine Translation16 Sept 202616 Sept 2026
Early-Bird Decoding: Accelerating Diffusion LLMs with Learnable Block Sizes and Parallel Sampling16 Sept 202616 Sept 2026
NepKANUN: A RAG-Based Nepali Legal Assistant16 Sept 202616 Sept 2026
Tables Decoded: DELTA for Structure, TARQA for Understanding16 Sept 202616 Sept 2026
Register Tokens for Bounded-State Reasoning in Diffusion Language Models16 Sept 202616 Sept 2026
Style-Debiased DPO: Updating LLM Knowledge with Factuality-Aware Synthetic Preference Data16 Sept 202616 Sept 2026
PunGraph: Retrieval-Enhanced Phonetic-Semantic Graph Reasoning for Pun Understanding16 Sept 202616 Sept 2026
An Empirical Study of Counterfactual Self-Explanations in LLMs16 Sept 202616 Sept 2026
Safe Error Correction for Language Models: Frozen-Base Adjustment with Capability Preservation16 Sept 202616 Sept 2026
Cross-Anatomy Transfer Versus Sparse Interpolation in Digital-Twin-Oriented Aortic Fluid-Structure Interaction Surrogates16 Sept 202616 Sept 2026
Bias-Induced Crossover in Absolute Capacity of Dense Associative Memory16 Sept 202616 Sept 2026
Observational Multiplicity16 Sept 202616 Sept 2026
Bio-Inspired Palette Evolution in Indirectly Encoded Substrates: Timescale Compatibility Shapes Activation Function Discovery16 Sept 202616 Sept 2026
Kernel-Based Metrics Learning for Uncertain Opponent Vehicle Trajectory Prediction in Autonomous Racing16 Sept 202616 Sept 2026
Goal-oriented probabilistic forecasting for dynamic PRB allocation in 5G networks16 Sept 202616 Sept 2026
Quantum-Inspired Trainable and Parameter-Efficient Tensor Networks for Image Inpainting16 Sept 202616 Sept 2026
Partial recovery of meter-scale surface weather16 Sept 202616 Sept 2026
Activation-Weighted Seeded Residual Coding for Low-Bit LLM Weight Repair16 Sept 202616 Sept 2026
Dual Randomized Smoothing: Beyond Global Noise Variance16 Sept 202616 Sept 2026
CoER: Defending against Adaptive Indirect Prompt Injection via Adversarial Co-Evolution and Refinement16 Sept 202616 Sept 2026
CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking16 Sept 202616 Sept 2026
R3: Robust Rubric-Agnostic Reward Models16 Sept 202616 Sept 2026
Script Fragmentation and Format: What Drives the English-Bengali Performance Gap in Open LLMs?16 Sept 202616 Sept 2026
Neural Stochastic Differential Equations on Compact State Spaces: Theory, Methods, and Application to Suicide Risk Modeling16 Sept 202616 Sept 2026
Generating Individual Travel Diaries Using Large Language Models Informed by Census and Land-Use Data16 Sept 202616 Sept 2026
Meta-Learning-Assisted Constraint Relaxation for Constrained Black-Box Optimization16 Sept 202616 Sept 2026
Do LLMs Make Neural Distinguishers Wise?16 Sept 202616 Sept 2026
Algorithms for adaptive and heteroskedastic linear regression at the computational threshold16 Sept 202616 Sept 2026

Provider changes

Provider changes 0

No provider listing or delisting between these dates

Hardware changes

Hardware changes 0

No hardware change between these dates

Other property changes

Other property changes 200

Openness, licence, status, parameters, release-date and other material property changes (context changes are listed above).

Other new entities

Other new entities 1

Other new entities
EntityTypeOrganizationFirst seen
Open RAIL-MLicense16 Sept 2026

Gone entities

Gone entities 0

No entity disappeared between these dates

“Gone” means an entity present at the first date is no longer current at the second (merged or retired) — its record and history are kept. Events are keyed on occurred_at; back-filled history is excluded (tick “include backfill” to add it). Per-entity history: any entity's History tab. Atlas as of 15 Sept 2026 · Methodology →